AsterNav: Autonomous Aerial Robot Navigation In Darkness Using Passive Computation

TL;DR

AsterNav tackles autonomous quadrotor navigation in complete darkness by marrying passive optical depth cues from a large-aperture coded lens with active structured lighting. The core advance is AsterNet, a dense-depth network trained entirely on synthetic data that generalizes zero-shot to real-world darkness, enabling dense metric depth on-board at 20 Hz. Coupled with a parsimonious obstacle-avoidance policy, the system demonstrates 95.5% navigation success across indoor and outdoor tests using only onboard sensing and computation. This work highlights the viability of co-designing passive optics with lightweight perception for energy-efficient, robust navigation in disaster scenarios where illumination is unavailable.

Abstract

Autonomous aerial navigation in absolute darkness is crucial for post-disaster search and rescue operations, which often occur from disaster-zone power outages. Yet, due to resource constraints, tiny aerial robots, perfectly suited for these operations, are unable to navigate in the darkness to find survivors safely. In this paper, we present an autonomous aerial robot for navigation in the dark by combining an Infra-Red (IR) monocular camera with a large-aperture coded lens and structured light without external infrastructure like GPS or motion-capture. Our approach obtains depth-dependent defocus cues (each structured light point appears as a pattern that is depth dependent), which acts as a strong prior for our AsterNet deep depth estimation model. The model is trained in simulation by generating data using a simple optical model and transfers directly to the real world without any fine-tuning or retraining. AsterNet runs onboard the robot at 20 Hz on an NVIDIA Jetson Orin$^\text{TM}$ Nano. Furthermore, our network is robust to changes in the structured light pattern and relative placement of the pattern emitter and IR camera, leading to simplified and cost-effective construction. We successfully evaluate and demonstrate our proposed depth navigation approach AsterNav using depth from AsterNet in many real-world experiments using only onboard sensing and computation, including dark matte obstacles and thin ropes (diameter 6.25mm), achieving an overall success rate of 95.5% with unknown object shapes, locations and materials. To the best of our knowledge, this is the first work on monocular, structured-light-based quadrotor navigation in absolute darkness.

Figures (11)

• Figure 1: AsterNav can estimate dense metric scene depth in complete darkness and navigate around it by using a large-aperture coded lens with a structured lighting source. The system is robust to unknown obstacles of different shapes, sizes, textures, and materials. The highlighted regions on the left illustrate how the projected dot pattern appears at different depths, exhibiting varying degrees of blur (blue to red denotes increasing depth in highlights). All the images in this paper are best viewed on a computer screen at 200% zoom at a 100% brightness.
• Figure 2: Robot is present in a scene (at $Z=0$) with two obstacles $O_1$ and $O_2$ at distances $Z_1$ (red) and $Z_2$ (blue) respectively. As the obstacles get closer (a) to (b), the distance between the two modes (each obstacle is represented by a mode in the depth distribution) gets smaller, making the depth segmentation harder. This is analogous to inter-class distribution in computer vision. See Suppl. § S.III. for more information.
• Figure 3: Coded Aperture and PSF Bank, with the camera focused at 0.5m. The intensities in all the images are inverted. denotes image inversion.
• Figure 4: Left to Right: Comparison between pinhole, fully open, and coded aperture images of dot patterns observed at 0.5m and 2.5m. The pinhole aperture maintains sharpness across depths, while the fully open and coded apertures introduce depth-dependent blur. The coded aperture exhibits more pronounced variations, thereby providing stronger cues for depth estimation.
• Figure 5: Synthetic data generation pipeline. $I_i, I_\text{ref}, I_\text{synth}$ are inverted.